INDEX

Explanations

terms related to fuel and energy sources

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

est

-0.21

es

-0.19

unto

-0.17

onto

-0.17

ese

-0.16

eg

-0.16

etta

-0.16

ew

-0.15

fe

-0.15

ect

-0.15

POSITIVE LOGITS

led

0.43

ing

0.26

LED

0.22

-efficient

0.21

lez

0.20

ING

0.20

ledon

0.20

ingu

0.19

lem

0.19

 tank

0.19

Activations Density 0.012%

terms related to fuel and energy sources

No Comments

No Known Activations